# Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench

arXiv: https://arxiv.org/abs/2512.02942 · HTML: https://mlsanity.com/paper/2512.02942/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 45 references that are in the map.
- First posted on arXiv 2 Dec 2025.

## Builds on (most cited first, 27 of 27)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [Seedance 1.0: Exploring the Boundaries of Video Generation Models](https://mlsanity.com/paper/2506.09113/) (2025)
- [VideoPhy: Evaluating Physical Commonsense for Video Generation](https://mlsanity.com/paper/2406.03520/) (2024)
- [T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation](https://mlsanity.com/paper/2407.14505/) (2024)
- [Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation](https://mlsanity.com/paper/2410.05363/) (2024)
- [Physion: Evaluating Physical Prediction from Vision in Humans and Machines](https://mlsanity.com/paper/2106.08261/) (2021)
- [VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation](https://mlsanity.com/paper/2503.06800/) (2025)
- [GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation](https://mlsanity.com/paper/2406.13743/) (2024)
- [WorldModelBench: Judging Video Generation Models As World Models](https://mlsanity.com/paper/2502.20694/) (2025)
- [VDT: General-purpose Video Diffusion Transformers via Mask Modeling](https://mlsanity.com/paper/2305.13311/) (2023)
- [Fr'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos](https://mlsanity.com/paper/2407.16124/) (2024)
- [Video-Bench: Human-Aligned Video Generation Benchmark](https://mlsanity.com/paper/2504.04907/) (2025)
- [VHELM: A Holistic Evaluation of Vision Language Models](https://mlsanity.com/paper/2410.07112/) (2024)
- [Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm](https://mlsanity.com/paper/2511.04570/) (2025)
- [VideoScore2: Think before You Score in Generative Video Evaluation](https://mlsanity.com/paper/2509.22799/) (2025)
- [SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models](https://mlsanity.com/paper/2510.08559/) (2025)
- [ExpVid: A Benchmark for Experiment Video Understanding & Reasoning](https://mlsanity.com/paper/2510.11606/) (2025)
- [PhysLab: A Benchmark Dataset for Multi-Granularity Visual Parsing of Physics Experiments](https://mlsanity.com/paper/2506.06631/) (2025)

## Built on by (most cited first, 7 of 7)

- [PhyGround: Benchmarking Physical Reasoning in Generative World Models](https://mlsanity.com/paper/2605.10806/) (2026)
- [PhyRPR: Training-Free Physics-Constrained Video Generation](https://mlsanity.com/paper/2601.09255/) (2026)
- [CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models](https://mlsanity.com/paper/2605.23699/) (2026)
- [Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains](https://mlsanity.com/paper/2608.09873/) (2026)
- [Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence](https://mlsanity.com/paper/2607.16401/) (2026)
- [MotionInsight: Diagnosing Object Motion Deficiencies in Generated Videos](https://mlsanity.com/paper/2609.37030/) (2026)
- [LabInstruct: Benchmarking Situated Instructional Video Generation for Lab Procedures](https://mlsanity.com/paper/2610.14020/) (2026)

## Abstract (arXiv)

The next frontier for video generation lies in developing models capable of zero-shot reasoning, where understanding real-world scientific laws is crucial for accurate physical outcome modeling under diverse conditions. However, existing video benchmarks are physical commonsense-based, offering limited insight into video models' scientific reasoning capability. We introduce VideoScience-Bench, a benchmark designed to evaluate undergraduate-level scientific understanding in video models. Each prompt encodes a composite scientific scenario that requires understanding and reasoning across multiple scientific concepts to generate the correct phenomenon. The benchmark comprises 200 carefully curated prompts spanning 14 topics and 103 concepts in physics and chemistry. We conduct expert-annotated evaluations across seven state-of-the-art video models in T2V and I2V settings along five dimensions: Prompt Consistency, Phenomenon Congruency, Correct Dynamism, Immutability, and Spatio-Temporal Continuity. Using a VLM-as-a-Judge to assess video generations, we observe strong correlation with human assessments. To the best of our knowledge, VideoScience-Bench is the first benchmark to evaluate video models not only as generators but also as reasoners, requiring their generations to demonstrate scientific understanding consistent with expected physical and chemical phenomena. Our data and evaluation code are available at: hrefhttps://github.com/hao-ai-lab/VideoSciencegithub.com/hao-ai-lab/VideoScience.